© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130846
    Prev
    Next
    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ĥçļĦ
    -0.26
    ä»ĸçļĦ
    -0.24
    彩
    -0.24
    ç¢İçīĩ
    -0.23
     Âł Âł Âł Âł
    -0.23
    ele
    -0.23
     Phonetic
    -0.23
    frag
    -0.23
    Fragment
    -0.22
     Âł Âł
    -0.22
    POSITIVE LOGITS
     NV
    0.26
    常å§Ķ
    0.25
    ä¸įä»ħåı¯ä»¥
    0.24
    isode
    0.23
     retrieves
    0.23
    _VOID
    0.23
    ESA
    0.23
    NV
    0.23
    asion
    0.23
    å¦Ĥæŀľçݩ家
    0.22
    Activations Density 0.120%

    No Known Activations